1A-profile CPU architecture support 2================================== 3 4QEMU's TCG emulation includes support for the Armv5, Armv6, Armv7 and 5Armv8 versions of the A-profile architecture. It also has support for 6the following architecture extensions: 7 8- FEAT_AA32BF16 (AArch32 BFloat16 instructions) 9- FEAT_AA32HPD (AArch32 hierarchical permission disables) 10- FEAT_AA32I8MM (AArch32 Int8 matrix multiplication instructions) 11- FEAT_AES (AESD and AESE instructions) 12- FEAT_BBM at level 2 (Translation table break-before-make levels) 13- FEAT_BF16 (AArch64 BFloat16 instructions) 14- FEAT_BTI (Branch Target Identification) 15- FEAT_CSV2 (Cache speculation variant 2) 16- FEAT_CSV2_1p1 (Cache speculation variant 2, version 1.1) 17- FEAT_CSV2_1p2 (Cache speculation variant 2, version 1.2) 18- FEAT_CSV2_2 (Cache speculation variant 2, version 2) 19- FEAT_CSV3 (Cache speculation variant 3) 20- FEAT_DGH (Data gathering hint) 21- FEAT_DIT (Data Independent Timing instructions) 22- FEAT_DPB (DC CVAP instruction) 23- FEAT_Debugv8p2 (Debug changes for v8.2) 24- FEAT_Debugv8p4 (Debug changes for v8.4) 25- FEAT_DotProd (Advanced SIMD dot product instructions) 26- FEAT_DoubleFault (Double Fault Extension) 27- FEAT_FCMA (Floating-point complex number instructions) 28- FEAT_FHM (Floating-point half-precision multiplication instructions) 29- FEAT_FP16 (Half-precision floating-point data processing) 30- FEAT_FRINTTS (Floating-point to integer instructions) 31- FEAT_FlagM (Flag manipulation instructions v2) 32- FEAT_FlagM2 (Enhancements to flag manipulation instructions) 33- FEAT_HCX (Support for the HCRX_EL2 register) 34- FEAT_HPDS (Hierarchical permission disables) 35- FEAT_I8MM (AArch64 Int8 matrix multiplication instructions) 36- FEAT_IDST (ID space trap handling) 37- FEAT_IESB (Implicit error synchronization event) 38- FEAT_JSCVT (JavaScript conversion instructions) 39- FEAT_LOR (Limited ordering regions) 40- FEAT_LPA (Large Physical Address space) 41- FEAT_LPA2 (Large Physical and virtual Address space v2) 42- FEAT_LRCPC (Load-acquire RCpc instructions) 43- FEAT_LRCPC2 (Load-acquire RCpc instructions v2) 44- FEAT_LSE (Large System Extensions) 45- FEAT_LVA (Large Virtual Address space) 46- FEAT_MTE (Memory Tagging Extension) 47- FEAT_MTE2 (Memory Tagging Extension) 48- FEAT_MTE3 (MTE Asymmetric Fault Handling) 49- FEAT_PAN (Privileged access never) 50- FEAT_PAN2 (AT S1E1R and AT S1E1W instruction variants affected by PSTATE.PAN) 51- FEAT_PAuth (Pointer authentication) 52- FEAT_PMULL (PMULL, PMULL2 instructions) 53- FEAT_PMUv3p1 (PMU Extensions v3.1) 54- FEAT_PMUv3p4 (PMU Extensions v3.4) 55- FEAT_RAS (Reliability, availability, and serviceability) 56- FEAT_RASv1p1 (RAS Extension v1.1) 57- FEAT_RDM (Advanced SIMD rounding double multiply accumulate instructions) 58- FEAT_RNG (Random number generator) 59- FEAT_S2FWB (Stage 2 forced Write-Back) 60- FEAT_SB (Speculation Barrier) 61- FEAT_SEL2 (Secure EL2) 62- FEAT_SHA1 (SHA1 instructions) 63- FEAT_SHA256 (SHA256 instructions) 64- FEAT_SHA3 (Advanced SIMD SHA3 instructions) 65- FEAT_SHA512 (Advanced SIMD SHA512 instructions) 66- FEAT_SM3 (Advanced SIMD SM3 instructions) 67- FEAT_SM4 (Advanced SIMD SM4 instructions) 68- FEAT_SPECRES (Speculation restriction instructions) 69- FEAT_SSBS (Speculative Store Bypass Safe) 70- FEAT_TLBIOS (TLB invalidate instructions in Outer Shareable domain) 71- FEAT_TLBIRANGE (TLB invalidate range instructions) 72- FEAT_TTCNP (Translation table Common not private translations) 73- FEAT_TTL (Translation Table Level) 74- FEAT_TTST (Small translation tables) 75- FEAT_UAO (Unprivileged Access Override control) 76- FEAT_VHE (Virtualization Host Extensions) 77- FEAT_VMID16 (16-bit VMID) 78- FEAT_XNX (Translation table stage 2 Unprivileged Execute-never) 79- SVE (The Scalable Vector Extension) 80- SVE2 (The Scalable Vector Extension v2) 81 82For information on the specifics of these extensions, please refer 83to the `Armv8-A Arm Architecture Reference Manual 84<https://developer.arm.com/documentation/ddi0487/latest>`_. 85 86When a specific named CPU is being emulated, only those features which 87are present in hardware for that CPU are emulated. (If a feature is 88not in the list above then it is not supported, even if the real 89hardware should have it.) The ``max`` CPU enables all features. 90 91R-profile CPU architecture support 92================================== 93 94QEMU's TCG emulation support for R-profile CPUs is currently limited. 95We emulate only the Cortex-R5 and Cortex-R5F CPUs. 96 97M-profile CPU architecture support 98================================== 99 100QEMU's TCG emulation includes support for Armv6-M, Armv7-M, Armv8-M, and 101Armv8.1-M versions of the M-profile architucture. It also has support 102for the following architecture extensions: 103 104- FP (Floating-point Extension) 105- FPCXT (FPCXT access instructions) 106- HP (Half-precision floating-point instructions) 107- LOB (Low Overhead loops and Branch future) 108- M (Main Extension) 109- MPU (Memory Protection Unit Extension) 110- PXN (Privileged Execute Never) 111- RAS (Reliability, Serviceability and Availability): "minimum RAS Extension" only 112- S (Security Extension) 113- ST (System Timer Extension) 114 115For information on the specifics of these extensions, please refer 116to the `Armv8-M Arm Architecture Reference Manual 117<https://developer.arm.com/documentation/ddi0553/latest>`_. 118 119When a specific named CPU is being emulated, only those features which 120are present in hardware for that CPU are emulated. (If a feature is 121not in the list above then it is not supported, even if the real 122hardware should have it.) There is no equivalent of the ``max`` CPU for 123M-profile. 124